26 resources
Helium New Tab is a lightweight, unofficial Helium browser new tab extension. Provides search, clock, date display and localization customization functions, supports automatic/manual theme switching and multi-language interface. Built on pure HTML/CSS/JS with no runtime dependencies, it is designed to optimize the new tab experience of the Helium browser.
Hide product video skills, use AI to reuse real product components and design language, and automatically generate software update promotional videos. It supports storyboard copywriting, original soundtrack, sound effects and code rendering, and is compatible with Claude Code and Codex, allowing developers to quickly produce professional promotional videos.
A high-performance word segmentation library launched by Hugging Face, specially optimized for research and production environments. It supports a variety of models and hardware, and provides bindings for languages such as Python for text preprocessing in natural language processing.
jevlint is an AI-based semantic code review tool used to detect issues that syntax checkers cannot identify (such as logs leaking keys). It defines rules through natural language, calls the AI model to evaluate the code and outputs probabilistic results. Supports ESLint integration and requires Node.js or Bun environment to run.
High-performance code-intelligent MCP server that indexes the code base into a persistent knowledge graph. Supports 158 languages, millisecond-level indexing and sub-millisecond queries, significantly reducing token consumption. Provides a single static binary file with zero dependencies, specially designed for AI programming agents to improve code understanding efficiency.
EdenText is a powerful native web-based word processor that supports docx and odt formats. It does not require a server or account, and all processing is done locally in the browser to ensure privacy and security. The application is small in size (less than 2MB for the first load), supports offline use, and provides a multi-language interface, suitable for editing needs from quick notes to long books.
DocJev is a document classification and splitting tool based on the Jev engine, supporting PDF, DOCX and other formats. Automatically identify document categories or boundaries through natural language rules, and provide CLI and Python library interfaces, which are suitable for efficient parsing and management of batch processing of complex document packages.
Jev Search is a web search engine based on TypeSafe Jev and Search1API. It supports natural language queries, automatically selecting sources, time ranges and ranking for relevance. Provides links, summaries, and editable filters, but does not generate answers. Supports iOS, Chrome and Edge installation as web applications.
Laya is a multilingual, non-autoregressive System 1 decision engine that supports typed decision making in more than 100 languages. It is trained through reinforcement learning to achieve a fast response of 33 milliseconds in a single forward pass, and has a router function that automatically selects checkpoints based on requests. It is suitable for scenarios that require low latency and high concurrency decision-making.
Doubao Say is a Linux voice input application based on GTK4, supporting Wayland and X11. It uses Beanbao or Volcano engine API to implement speech-to-text, provides multi-language settings, microphone selection and custom trigger shortcut key functions, aiming to bring a convenient voice interaction experience to Linux users.
Artemis is a Python-based Android automation framework that converts natural language instructions into reliable end-to-end workflows. It supports multi-modal AI assistant integration, has cross-application automation, element positioning and IDE diagnostic functions, and achieved a high success rate of 99%+ in the AndroidWorld benchmark test.
Scriptya is a script management tool that supports multiple languages such as Shell and Python. It provides fuzzy search running scripts, folder organization, custom icons and desktop application conversion functions, and integrates system menus and file managers (such as Nemo), supporting multi-language interfaces and complete history records.
Design Studio AI is an open source AI design workspace that supports human-machine collaboration to create web pages, 3D scenes and videos. Provides cloud editing, version control, multi-format export and MCP integration. BYOK is allowed to access various generative models, aiming to improve design efficiency through natural language interaction and manual editing.
Miles is an enterprise-oriented reinforcement learning framework designed for post-training of LLM and VLM. It supports efficient fine-tuning and optimization of multi-modal models and provides enterprise-level solutions designed to improve the performance and productivity of large-scale language and visual models.
This warehouse provides configurations, benchmarks, and ARM64 runtime images for reproducible large language model inference on a four-node NVIDIA DGX Spark cluster through a switchless direct connection. It is designed to demonstrate high-performance deployment solutions under specific hardware topologies, including detailed performance data and verification results.
OpenUI is a full-stack, renderer-agnostic generative UI framework built on a compact, streaming-first language. It provides official React support and built-in component library and chat interface. It is designed to generate UI with fewer tokens and is suitable for web application development.
Knap is a lightweight template language that converts data into Markdown through variables, filters, and logic. It is specially designed for the Obsidian ecosystem, provides CLI tools for batch rendering, and is integrated into applications as a library. Supports AST parsing, is safe and eval-free, and is suitable for automated note processing.
CAD-MCP is a CAD control service based on Python that drives software such as AutoCAD, GstarCAD and ZWCAD for drawing through natural language instructions. It supports line, graphic drawing and layer management to achieve CAD automation without manual operations. It is mainly targeted at Windows platform users.
InkOS is an AI Agent system for story creation and multi-language translation, supporting the generation of novels, scripts, interactive games and IP content. It unifiedly manages creativity, character setting, memory and review processes through intelligent agents, and provides multiple interactive forms such as Studio, TUI and CLI to help creators efficiently complete the entire process from conception to cross-language delivery.
TIS is an AI native data integration platform based on Flink and DataX. Supports natural language creation data pipeline, ChatBI intelligent question answering and Ontology knowledge graph. Provides Web UI, simplifies ETL process, has micro front-end scalability, and is suitable for enterprise-level DataOps scenarios.
local-llmup is a hardware-aware CLI tool for the management of local large language models. It provides an interactive terminal interface to evaluate the model's feasibility of running on the device (yes/slow/no) and estimated performance before downloading. Supports Ollama, llama.cpp and other backends to help users discover, install, service and manage the entire life cycle of local LLM.
zframes is an AI-driven personal market terminal framework. Users describe their needs through natural language, and the AI agent automatically generates JSON specifications and renders dashboards containing real-time financial data. It does not require an API key, supports multiple public data sources, and has self-correction capabilities, allowing AI to directly generate front-end interfaces without writing React code.
Makepad is a Rust-based AI accelerated application and game development platform that supports WebGL, Metal, DX11 and OpenGL. Provides high-performance UI runtime, editable design language and local LLM integration, suitable for building native and web applications, with rapid iteration capabilities.
quackd provides an LLM-driven brain for small robots to automatically plan and execute actions through natural language instructions. It supports 8 types of robots such as Microduck and a variety of large models, and has safety contract, memory and simulator functions to achieve intelligent interaction and autonomous control.
sherpa-onnx is an offline speech processing library based on ONNX Runtime, supporting functions such as ASR, TTS, speaker separation, enhancement, and VAD. It is suitable for various platforms such as embedded, Android, iOS, HarmonyOS, Raspberry Pi, NPU and servers. It provides 12 programming language interfaces and can run without the need for an Internet connection.
ad_agent is an advertising placement agent built based on Spring Boot and Spring AI. Supports natural language query effects, automatic price adjustment to improve ROI, creative generation and plan management. It integrates RAG and vector libraries, has multi-user isolation, long-term memory and SSE streaming interaction capabilities, and is suitable for intelligent decision-making in advertising scenarios.